def run(self, network, antecedents, out_attributes, user_options,
num_cores, outfile):
"""merge three signal file to generate a joined signal file"""
import os
from Betsy import module_utils
merge_node1, merge_node2 = antecedents
assert os.path.exists(merge_node1.identifier), \
'File not found: %s' % merge_node1.identifier
assert os.path.exists(merge_node2.identifier), \
'File not found: %s' % merge_node2.identifier
file1, file2 = module_utils.convert_to_same_platform(
merge_node1.identifier, merge_node2.identifier)
f = file(outfile, 'w')
module_utils.merge_two_files(file1, file2, f)
f.close()
def run(self, network, antecedents, out_attributes, user_options,
num_cores, outfile):
"""merge three signal file to generate a joined signal file"""
import os
from genomicode import filelib
from Betsy import module_utils
merge_node1, merge_node2 = antecedents
assert os.path.exists(merge_node1.identifier), (
'the merge_file1 %s in merge_data does not exist' %
merge_node1.identifier)
assert os.path.exists(merge_node2.identifier), (
'the merge_file2 %s in merge_data does not exist' %
merge_node2.identifier)
file1, file2 = module_utils.convert_to_same_platform(
merge_node1.identifier, merge_node2.identifier)
f = file(outfile, 'w')
module_utils.merge_two_files(file1, file2, f)
f.close()
assert filelib.exists_nz(outfile), (
'the output file %s for merge_data fails' % outfile)
def run(self, network, antecedents, out_attributes, user_options,
num_cores, outfile):
import subprocess
from Betsy import module_utils
from genomicode import config
rma_node, mas5_node = antecedents
scoresig_path = config.scoresig
scoresig_BIN = module_utils.which(scoresig_path)
assert scoresig_BIN, 'cannot find the %s' % scoresig_path
file1, file2 = module_utils.convert_to_same_platform(
rma_node.identifier, mas5_node.identifier)
command = [
'python', scoresig_BIN, '-r', file1, '-m', file2, '-j', '20', '-o',
outfile
]
process = subprocess.Popen(command,
shell=False,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
error_message = process.communicate()[1]
if error_message:
raise ValueError(error_message)
def run(
self, network, antecedents, out_attributes, user_options, num_cores,
outfile):
import os
import subprocess
import arrayio
from genomicode import filelib
from Betsy import read_label_file
from Betsy import module_utils
from genomicode import config
data_node_train, data_node_test, cls_node_train = antecedents
module_name = 'WeightedVoting'
gp_parameters = dict()
file1, file2 = module_utils.convert_to_same_platform(
data_node_train.identifier, data_node_test.identifier)
result, label_line, class_name = read_label_file.read(
cls_node_train.identifier)
M = arrayio.read(data_node_test.identifier)
label_line = ['0'] * M.dim()[1]
read_label_file.write('temp_test.cls', class_name, label_line)
gp_parameters['train.filename'] = file1
gp_parameters['train.class.filename'] = cls_node_train.identifier
gp_parameters['test.filename'] = file2
gp_parameters['test.class.filename'] = 'temp_test.cls'
if 'wv_num_features' in user_options:
gp_parameters['num.features'] = str(user_options['wv_num_features'])
if 'wv_minstd' in user_options:
assert module_utils.is_number(
user_options['wv_minstd']), 'the sv_minstd should be number'
gp_parameters['min.std'] = str(user_options['wv_minstd'])
wv_feature_stat = ['wv_snr', 'wv_ttest', 'wv_snr_median',
'wv_ttest_median', 'wv_snr_minstd', 'wv_ttest_minstd',
'wv_snr_median_minstd', 'wv_ttest_median_minstd']
assert out_attributes['wv_feature_stat'] in wv_feature_stat, (
'the wv_feature_stat is invalid'
)
gp_parameters['feature.selection.statistic'] = str(
wv_feature_stat.index(out_attributes['wv_feature_stat']))
gp_path = config.genepattern
gp_module = module_utils.which(gp_path)
assert gp_module, 'cannot find the %s' % gp_path
download_directory = os.path.join(".", 'wv_result')
command = [gp_module, module_name, '-o', download_directory]
for key in gp_parameters.keys():
a = ['--parameters', key + ':' + gp_parameters[key]]
command.extend(a)
process = subprocess.Popen(command,
shell=False,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
process.wait()
error_message = process.communicate()[1]
if error_message:
raise ValueError(error_message)
assert os.path.exists(download_directory), (
'there is no output directory for weightedVoting'
)
result_files = os.listdir(download_directory)
assert 'stderr.txt' not in result_files, 'gene_pattern get error'
gp_files = os.listdir(download_directory)
for gp_file in gp_files:
if gp_file.endswith('pred.odf'):
gp_file = os.path.join(download_directory, gp_file)
f = file(gp_file, 'r')
text = f.readlines()
f.close()
os.rename(os.path.join(download_directory, gp_file),
os.path.join(download_directory, 'prediction.odf'))
assert text[1][0:12] == 'HeaderLines='
start = int(text[1][12:-1])
newresult = [['Sample_name', 'Predicted_class', 'Confidence']]
for i in text[start + 2:]:
line = i.split()
n = len(line)
newline = [' '.join(line[0:n - 4]), line[n - 3], line[n - 2]]
newresult.append(newline)
f = file(outfile, 'w')
for i in newresult:
f.write('\t'.join(i))
f.write('\n')
f.close()
assert filelib.exists_nz(outfile), (
'the output file %s for classify_with_weighted_voting fails' % outfile
)